仿生資料庫

Database of Zinc-Tin Oxide Thin Film Transistor Electrical Characteristics(鋅錫氧化物薄膜電晶體特徵電性資料庫)

Introduction

According to its I_D-V_G curve, the electrical characteristics of a thin film transistor, such as the maximum and minimum currents, turn-on voltage, threshold voltage, carrier mobility, and subthreshold swing can be extracted. Through the experimental results, it is found that (1) the number of coated layers of zinc tin oxide film (that is, different thicknesses), (2) whether the oxide is patterned by lithography and etching, (3) the channel length, (4) measurement done in dark or under light (with the light wavelength of 405 nm), (5) the power density of the light will affect the I_D-V_G curves significantly. Therefore, this database selects these five factors as the setting parameters, and combines the neural network algorithm and the genetic algorithm to provide the electrical characteristics of the zinc tin oxide thin film transistors. The learning process is up to 1,000,000 times, the root mean square (RMS) error is less than 0.0014, and the false rate is less than 0.01.

從電晶體元件的汲極電流對閘極偏壓（I_D-V_G）曲線可以告訴我們元件的特徵電性，例如：電流最大值及最小值、電晶體開啟時電壓值 ，並且結合公式計算可以獲得元件的臨界電壓、載子遷移率、次臨界擺幅。透過實驗結果發現到：(1)塗佈不同層數(即厚度不同)的鋅錫氧化物薄膜，(2)有無進行微影蝕刻定義鋅錫氧化物薄膜面積，(3)源極電極和汲極電極間的通道長度，(4)在黑暗或照光(光源波長為405 nm)的情況下量測，(5)光源的強度不同等因素，都會造成線型變化。因此本資料庫挑選這五種影響I_D-V_G曲線線型的重要參數作為設定條件，結合類神經網路演算法和基因演算法，提供在不同參數條件下獲得的鋅錫氧化物薄膜電晶體元件特徵電性。學習程序為1,000,000次，均方根（RMS）誤差小於0.0014，誤率則小於0.01。